Udacity Deep Reinforcement Learning Nanodegree

Project Navigation

Introduction

For this project, you will train an agent to navigate (and collect bananas!) in a large, square world.

In the project an agent has to learn to collect the maximum number of bananas randomly spread inside a virtual playground. The agent can do basic movement (turning and moving) and every time he find a banana he gets a reward. If the banana is yellow he increases the score, and if case he hits a blue banana, the score decreases by 1. The goal of the agent is to maximize the reward score.

The solution of this environment was attempted by implementation a Deep Q-network (DQN) algorithm. The DQN algorithm is a reinforcement learning application via the implementation of Q-learning method combined with a deep learning network.

A reward of +1 is provided for collecting a yellow banana, and a reward of -1 is provided for collecting a blue banana. Thus, the goal of your agent is to collect as many yellow bananas as possible while avoiding blue bananas.

The state space has 37 dimensions and contains the agent's velocity, along with ray-based perception of objects around agent's forward direction. Given this information, the agent has to learn how to best select actions. Four discrete actions are available, corresponding to:

• 0 - move forward.
• 1 - move backward.
• 2 - turn left.
• 3 - turn right.

The task is episodic, and in order to solve the environment, your agent must get an average score of +13.

Getting Started

1. Download the environment from one of the links below. You need only select the environment that matches your operating system:

   • Linux: click here
   • Mac OSX: click here
   • Windows (32-bit): click here
   • Windows (64-bit): click here

   (For Windows users) Check out this link if you need help with determining if your computer is running a 32-bit version or 64-bit version of the Windows operating system.

   (For AWS) If you'd like to train the agent on AWS (and have not enabled a virtual screen), then please use this link to obtain the environment.

2. Place the file in the DRLND GitHub repository, in the p1_navigation/ folder, and unzip (or decompress) the file.

Report

The final report summarizing the code implementation and my solution of the environemnt is in the report.md